Gemma 3 4B pricing.

Prices checked

Gemma 3 4B costs $0.05 in and $0.10 out per million tokens from OpenRouter; the cheapest price is $0.04 at Kilo Gateway, checked .

OpenRouter's own price

OpenRouter

$0.06/M tokens

$0.05 in · $0.10 out

93% below the typical price of the 392 text models we track.

Cheapest price

Kilo Gateway

$0.04/M tokens

$0.04 in · $0.05 out

32% less than OpenRouter, and the provider says why.

reads imagesstructured outputopen weights131k contextreleased 13 Mar 2025

Every provider selling Gemma 3 4B

  1. 1

    Kilo Gateway

    Promotion

    $0.04 in · $0.05 out

    $0.04/M tokens
  2. 2

    Parasail

    Runs it themselves

    $0.04 in · $0.05 out

    $0.04/M tokens
  3. 3

    Merge Gateway

    Runs it themselves

    $0.04 in · $0.08 out · 128k context here

    $0.05/M tokens
  4. 4

    $0.04 in · $0.08 out

    $0.05/M tokens
  5. 5

    OpenRouter

    Same as maker

    $0.05 in · $0.10 out

    $0.06/M tokens
  6. 6

    $0.05 in · $0.10 out

    $0.06/M tokens
  7. 7

    DeepInfra

    Same as maker

    $0.05 in · $0.10 out

    $0.06/M tokens
  8. 8

    Eden AI

    Same as maker

    $0.05 in · $0.10 out

    $0.06/M tokens
  9. 9

    DeepInfra

    Same as maker

    $0.05 in · $0.10 out

    $0.06/M tokens
  10. 10

    DeepInfra

    Same as maker

    $0.05 in · $0.10 out

    $0.06/M tokens
  11. 11

    Inference.net

    Same as maker

    $0.05 in · $0.10 out

    $0.06/M tokens
  12. 12

    AI/ML API

    Costs more

    $0.05 in · $0.11 out

    $0.07/M tokens
  13. 13

    NanoGPT

    Costs more

    $0.20 in · $0.20 out · 128k context here

    $0.20/M tokens

Not ranked

Below the maker's own price with nothing published to account for it, from a catalog we could not read reliably, or a free tier, which is a limit rather than a price. Why

  1. NVIDIA build

    Free tier

    given away with limits

    free
  2. Featherless

    Not ranked

    $0.05 in · $0.10 out · 33k context here

    $0.06/M tokens

Something else wrong?

What it costs for your work
pages a month
$0.04

A month at OpenRouter's own price

$0.03

A month at Kilo Gateway, the cheapest

under $0.01

What you save

A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.

Run it yourself

On a server by the month

Google publishes the weights, so you can run Gemma 3 4B on a server you rent by the month. It needs about 5.1 GB of RAM on a CPU, and the cheapest plan we track with that much and a disk included is Leaseweb VPS 2 at $9.04 a month, streaming about 5.5–11 tok/s. Every plan that fits

On a GPU by the hour

The RTX A5000 holds Gemma 3 4B in 24 GB of memory against the 5.1 GB the weights, the context and the runtime need. The cheapest one we track is RunPod's RTX A5000 · Community Cloud at $0.16/GPU-hr, which is $116.80 for the 730 hours in a month, checked 31 Oct. Every GPU price

How we count

Prices are per million tokens. The big number on each row is blended 3 in : 1 out, the way most work uses a model. A price below OpenRouter's own is listed as cheapest only when the provider says why. Google trained Gemma 3 4B and sells it on no catalog we read, so the price every row is measured against is OpenRouter's.

Promotion
A discount the provider publishes, which may end.
Runs it themselves
The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
Resells
The provider sells another company's endpoint, at a margin of its own or at the maker's price.
Same as maker
Sold by someone else at the price the maker charges.
Costs more
Sold by someone else for more than the maker charges.
Free tier
Given away inside a quota. A limit is not a price, so it is never called cheapest.
Not ranked
Below the maker's price on a closed model with nothing to account for it, or from a catalog we could not read reliably. Listed, and never a pick.

Similar models

Models from other labs that do what Gemma 3 4B does, cheapest first. Each percentage is against Gemma 3 4B's cheapest price, $0.04 per M tokens.

Frequently asked

Who sells Gemma 3 4B cheapest?
Kilo Gateway, at $0.04 in and $0.05 out per million tokens, checked 31 Oct 2026. A discount the provider publishes, which may end.
Is Gemma 3 4B open weights?
Yes. Google publishes the weights, so anyone may host Gemma 3 4B, which is why 12 providers sell it and why their prices differ so much.
How much context does Gemma 3 4B hold?
131,072 tokens in one call, which is about 131k.
How does Gemma 3 4B compare with the rest of the market?
At $0.06 per million tokens, OpenRouter's own price is 93% below the typical $0.88 across the 392 text models we track.

More from Google

Ranked in